Dynamic cardinality-based group segmentation

Abstract

Systems and methods are provided for analysis and selection of attributes used to segment data entities. The attributes used to segment data entities may be analyzed to identify segments of data entities (e.g., distinct audiences of visitors) that share values for a given subset of attributes. By intelligently selecting attributes for use in the segmentation process based on the values that they may take (e.g., the cardinality of the attributes), the selected attributes can be used to generate a reasonable or otherwise desirable number of data entity segments. Other attributes can be excluded from the segmentation process.

What is claimed is: 
     
       1. A system comprising:
 computer-readable memory storing executable instructions; and 
 one or more processors programmed by the executable instructions to at least:
 obtain attribute data representing values of an attribute for each of a plurality of visitor data entities, wherein a first visitor data entity of the plurality of visitor data entities represents a first visitor to a content site; 
 determine that the attribute data fails to satisfy a cardinality criterion; 
 in response to determining that the attribute data fails to satisfy the cardinality criterion:
 determine to reduce cardinality of the attribute data; 
 generate a plurality of attribute value subsets from the attribute data, wherein the plurality of attribute value subsets comprises:
 a first attribute value subset associated with a first subset of values represented by the attribute data; and 
 a second attribute value subset associated with a second subset of values represented by the attribute data; and 
 
 determine that the plurality of attribute value subsets satisfies the cardinality criterion; 
 
 generate a plurality of visitor data entity segments using the plurality of attribute value subsets and the plurality of visitor data entities, wherein a first visitor data entity segment of the plurality of visitor data entity segments comprises visitor data entities associated with a first attribute value subset of the plurality of attribute value subsets, and wherein a second visitor data entity segment of the plurality of visitor data entity segments comprises visitor data entities associated with a second attribute value subset of the plurality of attribute value subsets; and 
 generate a user interface using the plurality of visitor data entity segments, wherein the user interface enables a user to initiate at least one of: modification of a cardinality of the attribute, or modification of the plurality of visitor data entity segments. 
 
 
     
     
       2. The system of  claim 1 , wherein first attribute data for the first visitor data entity comprises data generated during a visit of the first visitor to the content site. 
     
     
       3. The system of  claim 1 , wherein the one or more processors programmed to determine that the attribute data fails to satisfy the cardinality criterion are programmed by further executable instructions to determine that a quantity of distinct values represented by the attribute data fails to satisfies a threshold. 
     
     
       4. The system of  claim 3 , wherein the threshold comprises a maximum threshold. 
     
     
       5. The system of  claim 3 , wherein the threshold comprises a minimum threshold. 
     
     
       6. The system of  claim 1 , wherein the one or more processors programmed to generate the plurality of attribute value subsets are programmed by further executable instructions to execute a clustering algorithm. 
     
     
       7. The system of  claim 1 , wherein the one or more processors programmed to generate the plurality of attribute value subsets are programmed by further executable instructions to generate a set of discrete values, wherein individual discrete values are associated with a portion of continuous values represented by the attribute data. 
     
     
       8. The system of  claim 1 , wherein the one or more processors are programmed by further executable instructions to:
 receive interaction data representing a modification to a cardinality parameter associated with the attribute; and 
 generate a second plurality of attribute value subsets from the attribute data, wherein the second plurality of attribute value subsets is generated based on the modification to the cardinality parameter. 
 
     
     
       9. The system of  claim 1 , wherein the one or more processors are programmed by further executable instructions to:
 receive interaction data representing a selection of a second attribute from a set of candidate attributes; and 
 generate a second plurality of visitor data entity segments from the plurality of visitor data entities, wherein the second plurality of visitor data entity segments is generated based on the second attribute. 
 
     
     
       10. The system of  claim 1 , wherein the one or more processors are programmed by further executable instructions to:
 receive interaction data representing a modification to a segmentation parameter associated generating the plurality of visitor data entity segments; and 
 generate a second plurality of visitor data entity segments from the plurality of visitor data entities, wherein the second plurality of visitor data entity segments is generated based on the modification to the segmentation parameter. 
 
     
     
       11. The system of  claim 1 , The system of  claim 1 , wherein the one or more processors are programmed by further executable instructions to generate content targeting data based on the first visitor data entity segment. 
     
     
       12. A computer-implemented method comprising:
 under control of a computing system comprising one or more processors configured to execute specific instructions,
 obtaining first attribute data representing values of a first attribute for each of a plurality of data entities, wherein a first data entity of the plurality of data entities represents a first visitor to a content site; 
 determining that the first attribute data satisfies a cardinality criterion; 
 adding the first attribute to a set of candidate attributes; 
 obtaining second attribute data representing values of a second attribute for each of the plurality of data entities; 
 determining that the second attribute data fails to satisfy the cardinality criterion; 
 determining, based on the second attribute data failing to satisfy the cardinality criterion, to generate third attribute data with a lower degree of cardinality than the second attribute data; 
 generating the third attribute data representing values of a third attribute, wherein the third attribute corresponds to the second attribute with the lower degree of cardinality; 
 determining that the third attribute data satisfies the cardinality criterion; 
 adding the third attribute to the set of candidate attributes; 
 generating a plurality of data entity segments using the set of candidate attributes and the plurality of data entities; and 
 generate a user interface using the plurality of data entity segments, wherein the user interface enables a user to initiate at least one of: modification of a cardinality of an attribute, or modification of the plurality of data entity segments. 
 
 
     
     
       13. The computer-implemented method of  claim 12 , further comprising:
 obtaining fourth attribute data representing values of a fourth attribute for each of the plurality of data entities; 
 determining that the fourth attribute data fails to satisfy the cardinality criterion; 
 generating fifth attribute data representing values of a fifth attribute, wherein the fifth attribute corresponds to the fourth attribute with a reduced degree of cardinality; 
 determining that the fifth attribute data fails to satisfies the cardinality criterion; and 
 excluding the fifth attribute from the set of candidate attributes. 
 
     
     
       14. The computer-implemented method of  claim 12 , wherein generating the plurality of data entity segments comprises executing a clustering algorithm using the first attribute data and the third attribute data. 
     
     
       15. The computer-implemented method of  claim 12 , wherein determining that the first attribute data fails to satisfy the cardinality criterion comprises determining that a quantity of distinct values represented by the first attribute data fails to satisfies a threshold. 
     
     
       16. The computer-implemented method of  claim 12 , further comprising generating a user interface using the plurality of data entity segments, wherein the user interface enables a user to initiate at least one of: modification of a cardinality of a candidate attribute, or modification of the plurality of data entity segments. 
     
     
       17. The computer-implemented method of  claim 16 , further comprising:
 receiving interaction data representing a modification to a cardinality parameter associated with the third attribute; and 
 generating fourth attribute data representing values of a fourth attribute, wherein the fourth attribute corresponds to the third attribute with a modified degree of cardinality. 
 
     
     
       18. The computer-implemented method of  claim 16 , further comprising:
 receiving interaction data representing a selection of a fourth attribute from the set of candidate attributes; and 
 generating a second plurality of data entity segments from the plurality of data entities, wherein the second plurality of data entity segments is generated based on the fourth attribute. 
 
     
     
       19. The computer-implemented method of  claim 16 , further comprising:
 receiving interaction data representing a modification to a segmentation parameter associated generating the plurality of data entity segments; and 
 generating a second plurality of data entity segments from the plurality of data entities, wherein the second plurality of data entity segments is generated based on the modification to the segmentation parameter. 
 
     
     
       20. The computer-implemented method of  claim 12 , further comprising sending data representing the plurality of data entity segments to a visitor processing system configured to manage types of data tracked for different visitors of a content site.